딥러닝 공부방

Learning Representations by Maximizing Mutual Information Across Views Philip Bachman, R Devon Hjelm arXiv 2019 PDF, SSL By SeonghoonYu August 8th, 2021 Summary (1) 하나의 이미지에 random augmentation을 적용하여 두 개의 view (x1, x2) 를 생성합니다. (2) 각각을 encoder에 전달합니다. f(x1), f(x2) (3) f(x1), f(x2)의 feature map의 index 사이의 상호정보량을 계산합니다. feature map은 1-to-5, 1-to-7, 5-to-5 로 설정하며 index는 uniform하게 sample 합니다. Loss는 ..

Contrastive Multiview Coding Yonglong Tian, Dilip Krishnan, Phillip Isola, arXiv 2019 PDF, SSL By SeonghoonYu August 6th, 2021 Summary 논문 제목 그대로 multiview 간의 상호 정보량을 최대화하여 학습합니다. 한 이미지내의 multiview는 밝기, 색상, 뎁스, 옵티컬 플로우가 될 수 있습니다. classification의 경우에 이미지 색상 공간을 Y, ab 변환하여 동일 이미지의 Y와 ab는 positive, 다른 이미지의 ab는 negative로 NCE Loss를 최소화하여 학습합니다. 이외에도 추가적인 view로 depth를 사용할 수 있습니다. view 개수와 동일한 encoder 개..

Unsupervised Representation Learning by Pre-diction Image Rotations Spyros Gidaris, Praveer Singh, Nikos Komodakis, arXiv 2018 PDF, SSL By SeonghoonYu August 4th, 2021 Summary The ConvNet is trained on the 4-way image classification task of recognizing one of the four image rotation(0, 90, 180, 270). The task of predicting rotation transformations provides a powerful surrogate supervision signel..

Invariant Information Clustering for Unsupervised Image Classification and Segmentation Xu Ji, Joao F.Henriques, Andrea Vedaldi, arXiv 2018 PDF, Clustering By SeonghoonYu July 30th, 2021 Summary This paper presents IIC model which acieves SOTA performance on Image clustering and Image segmentation by maximizing the mutual information between the original image and the transformed image from orig..

Big Self-Supervised Models are Strong Semi-Supervised Learners Ting Chen, Simon Kornblith, Kevin Swersky, Mohammad Norouzi, Geoffrey Hinton arXiv 2020 PDF, SSL By SeonghoonYu July 26th, 2021 Summary This paper achieves SOTA performance by combine the pre-trained model on self-supervised learning with knowledge distilation. Namely, They show that using pre-trained model on SSL as teacher model fo..

Unsupervised Learning of Visual Representations using Videos Xiaolong Wang, Abhinav Gupta, arXiv 2015 PDF, Video By SeonghoonYu July 23th, 2021 Summary This paper use hundreds of thousands of unlabeled videos from the web to learn visual representations. They use the first frame and the last frame in same video as positive samples and a random frame from different video as negative sample. They ..

Unsupervised Feature Learning via Non-Parametric Instance Discrimination Zhirong Wu, Yuanjun Xiong, Stella X.Yu, Dahua Lin, arXiv 2018 PDF, Self-Suervised Learning, By SeonghoonYu, July 22th, 2021 Summary The feature representations can be learned by discriminating among individual instances without any notion of semantic categories. We can find that Figure shows an image from class leopard is r..

Learning Deep Representations by Mutual Information Estimation and Maximization R Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, arXiv 2018 PDF, SSL By SeonghoonYu July 21th, 2021 Summary This paper updates model's parameters by maximizing mutial information between immediate feature maps and flattened last feature maps obtained from ConvNet. To do this, they use Jensen-Shannon divergence(..

Deep Clustering for Unsupervised Learning of Visual Features Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze, arXiv 2018 PDF, Self Supervised Learning By SeonghoonYu July 15th, 2021 Summary This paper is clustering based self-supervised learning in an offline fashion. This model jointly learns the parameters of a neural network and the cluster assignments of the resulting feature..

Unsupervised Learning of Visual Features by Contrasting Cluster Assignments Mathilde Caron, Ishan Misra, Jullien Mairal, Priya Goyal, Piotr Bojanowski, Armand Joulin arxiv 2020 PDF, Self-Supervised Learning By SeonghoonYu July 19th, 2021 Summary This paper propose an online clustering-based self-supervised method learning visual features in an online fashion without supervision Typical clusterin..